(I'm just back from vacation) On Mon, Oct 11, 2021 at 11:28:10AM +0200, Michal Hocko wrote: > On Fri 08-10-21 10:17:50, David Hildenbrand wrote: > > On 08.10.21 08:39, ultrachin@xxxxxxx wrote: > > > From: chen xiaoguang <xiaoggchen@xxxxxxxxxxx> > > > > > > The exit time is long when program allocated big memory and > > > the most time consuming part is free memory which takes 99.9% > > > of the total exit time. By using async free we can save 25% of > > > exit time. > > > > > > Signed-off-by: chen xiaoguang <xiaoggchen@xxxxxxxxxxx> > > > Signed-off-by: zeng jingxiang <linuszeng@xxxxxxxxxxx> > > > Signed-off-by: lu yihui <yihuilu@xxxxxxxxxxx> > > > > I recently discussed with Claudio if it would be possible to tear down the > > process MM deferred, because for some use cases (secure/encrypted > > virtualization, very large mmaps) tearing down the page tables is already > > the much more expensive operation. > > > > There is mmdrop_async(), and I wondered if one could reuse that concept when > > tearing down a process -- I didn't look into feasibility, however, so it's > > just some very rough idea. > > This is not a new problem. Large process tear down can take ages. The > primary road block has been accounting. This lot of work has to be > accounted to the proper domain (e.g. cpu cgroup). A deferred and > properly accounted context implementation is still lacking AFAIK. Right, still doesn't exist. It's coming though, and there was a session on it at LPC this year[1]. > I have a vague recollection we have padata framework but I am not sure > anybody has explored this to be used for the address space shutdown. > IIRC Daniel Jordan was active in that area. Yeah, address space teardown is one of the things we want to use padata for. It's on the list. [1] https://linuxplumbersconf.org/event/11/contributions/1041/
